Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4410 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.5421. Min Act: 0.0000

Data Index: 982864 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4965. Min Act: -0.0000

Data Index: 825882 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.4734. Min Act: -0.0000

Data Index: 989551 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1173781 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3878. Min Act: -0.0000

Data Index: 90972 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3882. Min Act: -0.0000

Data Index: 445406 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3626. Min Act: 0.0000

Data Index: 417183 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3515. Min Act: 0.0000

Data Index: 971641 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3372. Min Act: -0.0000

Data Index: 551885 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1322801 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1003779 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3000. Min Act: 0.0000

Data Index: 529621 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2825. Min Act: -0.0000

Data Index: 905439 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2698. Min Act: -0.0000

Data Index: 675455 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2747. Min Act: 0.0000

Data Index: 1334152 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2743. Min Act: -0.0000

Data Index: 549085 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2732. Min Act: -0.0000

Data Index: 579358 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2682. Min Act: -0.0000

Data Index: 502411 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2651. Min Act: -0.0000

Data Index: 917284 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1105787 (C4 (Web Text))

Max Activating Token Index: 421